From patchwork Tue Oct 20 09:33:37 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lorenzo Bianconi X-Patchwork-Id: 11846141 X-Patchwork-Delegate: kuba@kernel.org Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-13.1 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id AEAE9C433E7 for ; Tue, 20 Oct 2020 09:33:58 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 4ADB2223FB for ; Tue, 20 Oct 2020 09:33:58 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1603186438; bh=TO2mQCrZ4gEjafEEdiwpDNPoeRvJOuZg3DXkV4CWg28=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=g8qILYwoXuw8HAWgFi+Cn4E8mA6rpqEfP1NJwtHKnb0Hct7DN3uDMgiDzDJ5VVr9d HXOE+kJSEnORRmb3LyeAfTC+CEkUn/N6Ti92Cd/RwJPF+aU3hK6xgX7eYR2g7dgCvR yesG/jo1mIr7bHGKL0/PzswC8aMTKW+eymLiQb8g= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2392435AbgJTJd5 (ORCPT ); Tue, 20 Oct 2020 05:33:57 -0400 Received: from mail.kernel.org ([198.145.29.99]:52034 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2391743AbgJTJd5 (ORCPT ); Tue, 20 Oct 2020 05:33:57 -0400 Received: from lore-desk.redhat.com (unknown [151.66.125.178]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 2AF3F222C8; Tue, 20 Oct 2020 09:33:54 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1603186436; bh=TO2mQCrZ4gEjafEEdiwpDNPoeRvJOuZg3DXkV4CWg28=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=LkMyuuKIVERtvrttDWafGL6YELuB2LbGvLNaH9a1Xxk3sFOSt605jPaWBo7xwHegU NskvCh2AC9LEhxJqq+RAnJEqCHybth1idKwr2qXmanKepTBmlbMs7+p3rvihqEgxFi 6o0O5FJzvE1f5m5z0k/FMFF3r3D0bUPEuj7hSra4= From: Lorenzo Bianconi To: netdev@vger.kernel.org Cc: bpf@vger.kernel.org, davem@davemloft.net, kuba@kernel.org, lorenzo.bianconi@redhat.com, brouer@redhat.com, ilias.apalodimas@linaro.org Subject: [RFC 1/2] net: xdp: introduce bulking for xdp tx return path Date: Tue, 20 Oct 2020 11:33:37 +0200 Message-Id: <62165fcacf47521edae67ae739827aa5f751fb8b.1603185591.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.26.2 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org X-Patchwork-State: RFC Introduce bulking capability in xdp tx return path (XDP_TX and XDP_REDIRECT). xdp_return_frame and xdp_return_frame_napi are usually run inside the driver NAPI tx completion loop so it is possible batch them. Current implementation considers only page_pool memory model. Convert mvneta driver to xdp_return_frame_bulk APIs. Suggested-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi --- drivers/net/ethernet/marvell/mvneta.c | 8 ++--- include/net/xdp.h | 11 ++++++ net/core/xdp.c | 50 +++++++++++++++++++++++++++ 3 files changed, 65 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 54b0bf574c05..af33cc62ed4c 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -663,6 +663,8 @@ struct mvneta_tx_queue { /* Affinity mask for CPUs*/ cpumask_t affinity_mask; + + struct xdp_frame_bulk bq; }; struct mvneta_rx_queue { @@ -1854,12 +1856,10 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp, dev_kfree_skb_any(buf->skb); } else if (buf->type == MVNETA_TYPE_XDP_TX || buf->type == MVNETA_TYPE_XDP_NDO) { - if (napi && buf->type == MVNETA_TYPE_XDP_TX) - xdp_return_frame_rx_napi(buf->xdpf); - else - xdp_return_frame(buf->xdpf); + xdp_return_frame_bulk(buf->xdpf, &txq->bq, napi); } } + xdp_flush_frame_bulk(&txq->bq, napi); netdev_tx_completed_queue(nq, pkts_compl, bytes_compl); } diff --git a/include/net/xdp.h b/include/net/xdp.h index 3814fb631d52..4b79d50afe36 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -104,6 +104,12 @@ struct xdp_frame { struct net_device *dev_rx; /* used by cpumap */ }; +#define XDP_BULK_QUEUE_SIZE 16 +struct xdp_frame_bulk { + void *q[XDP_BULK_QUEUE_SIZE]; + int count; + void *xa; +}; static inline struct skb_shared_info * xdp_get_shared_info_from_frame(struct xdp_frame *frame) @@ -194,6 +200,11 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); +void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq, + bool napi_direct); +void xdp_return_frame_bulk(struct xdp_frame *xdpf, + struct xdp_frame_bulk *bq, + bool napi_direct); /* When sending xdp_frame into the network stack, then there is no * return point callback, which is needed to release e.g. DMA-mapping diff --git a/net/core/xdp.c b/net/core/xdp.c index 48aba933a5a8..b05467a916b4 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -380,6 +380,56 @@ void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); +void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq, + bool napi_direct) +{ + struct xdp_mem_allocator *xa = bq->xa; + int i; + + for (i = 0; i < bq->count; i++) { + napi_direct &= !xdp_return_frame_no_direct(); + page_pool_put_full_page(xa->page_pool, + virt_to_head_page(bq->q[i]), + napi_direct); + } + bq->count = 0; +} +EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk); + +void xdp_return_frame_bulk(struct xdp_frame *xdpf, + struct xdp_frame_bulk *bq, + bool napi_direct) +{ + struct xdp_mem_info *mem = &xdpf->mem; + struct xdp_mem_allocator *xa, *nxa; + + if (mem->type != MEM_TYPE_PAGE_POOL) { + __xdp_return(xdpf->data, &xdpf->mem, napi_direct); + return; + } + + rcu_read_lock(); + + xa = bq->xa; + if (unlikely(!xa || mem->id != xa->mem.id)) { + nxa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); + if (unlikely(!xa)) { + bq->xa = nxa; + xa = nxa; + } + } + + if (mem->id != xa->mem.id || bq->count == XDP_BULK_QUEUE_SIZE) + xdp_flush_frame_bulk(bq, napi_direct); + + bq->q[bq->count++] = xdpf->data; + if (mem->id != xa->mem.id) + bq->xa = nxa; + + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(xdp_return_frame_bulk); + void xdp_return_buff(struct xdp_buff *xdp) { __xdp_return(xdp->data, &xdp->rxq->mem, true); From patchwork Tue Oct 20 09:33:38 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lorenzo Bianconi X-Patchwork-Id: 11846139 X-Patchwork-Delegate: kuba@kernel.org Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-13.1 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 83561C433E7 for ; Tue, 20 Oct 2020 09:34:01 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 30F15222E8 for ; Tue, 20 Oct 2020 09:34:01 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1603186441; bh=M5WlBZtyTGQG1tc8djGKTOxquF2qQdaDPsN9eWxctO8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=Igkyp/7Fe1t34G1FuXy9f+7RicrZx2Gdr5ozkkUkjXYWKGQNhHVAeUsXzCWMsGgdW SJdrZR3Whkb392s5QuxIXnISlbKLLfI6zxfJzHYvotSnc+lB1uJEHm5VhaCWOTGOWz t7E0UkYrb3C24BkJDRoYhuxLbAzLk2MDgiN8VXFo= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2392871AbgJTJeA (ORCPT ); Tue, 20 Oct 2020 05:34:00 -0400 Received: from mail.kernel.org ([198.145.29.99]:52072 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2392766AbgJTJeA (ORCPT ); Tue, 20 Oct 2020 05:34:00 -0400 Received: from lore-desk.redhat.com (unknown [151.66.125.178]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id E1B44223C6; Tue, 20 Oct 2020 09:33:57 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1603186439; bh=M5WlBZtyTGQG1tc8djGKTOxquF2qQdaDPsN9eWxctO8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=UDps+fJCjLNACla8cYhgBtnnNhjY+NCq5yLo+yh8+2AIgtgVc68GUQxMuzi9co2h5 ngquHz3DJsl7WVIPXIAcLwU+ncxjbnngjmhXw+gqzC0T0J6EQ7vDiZLQ9VUHlAO1i2 05PquipGaaL2BuhophGsmvDZGrzwopNhnAj/dvqc= From: Lorenzo Bianconi To: netdev@vger.kernel.org Cc: bpf@vger.kernel.org, davem@davemloft.net, kuba@kernel.org, lorenzo.bianconi@redhat.com, brouer@redhat.com, ilias.apalodimas@linaro.org Subject: [RFC 2/2] net: page_pool: add bulk support for ptr_ring Date: Tue, 20 Oct 2020 11:33:38 +0200 Message-Id: <5017913dc83b31ef389c804f0c560e25746b3506.1603185591.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.26.2 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org X-Patchwork-State: RFC Introduce the capability to batch page_pool ptr_ring refill since it is usually run inside the driver NAPI tx completion loop. Suggested-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi --- include/net/page_pool.h | 21 +++++++++++++++++++++ net/core/page_pool.c | 37 +++++++++++++++++++++++++++++++++++++ net/core/xdp.c | 13 ++++++------- 3 files changed, 64 insertions(+), 7 deletions(-) diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 81d7773f96cd..1330419efec7 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -169,6 +169,8 @@ static inline void page_pool_release_page(struct page_pool *pool, void page_pool_put_page(struct page_pool *pool, struct page *page, unsigned int dma_sync_size, bool allow_direct); +void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count, + bool allow_direct); /* Same as above but will try to sync the entire area pool->max_len */ static inline void page_pool_put_full_page(struct page_pool *pool, @@ -215,4 +217,23 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) if (unlikely(pool->p.nid != new_nid)) page_pool_update_nid(pool, new_nid); } + +static inline void page_pool_ring_lock(struct page_pool *pool) + __acquires(&pool->ring.producer_lock) +{ + if (in_serving_softirq()) + spin_lock(&pool->ring.producer_lock); + else + spin_lock_bh(&pool->ring.producer_lock); +} + +static inline void page_pool_ring_unlock(struct page_pool *pool) + __releases(&pool->ring.producer_lock) +{ + if (in_serving_softirq()) + spin_unlock(&pool->ring.producer_lock); + else + spin_unlock_bh(&pool->ring.producer_lock); +} + #endif /* _NET_PAGE_POOL_H */ diff --git a/net/core/page_pool.c b/net/core/page_pool.c index ef98372facf6..03c3a92c9179 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -11,6 +11,8 @@ #include #include +#include + #include #include #include @@ -408,6 +410,41 @@ void page_pool_put_page(struct page_pool *pool, struct page *page, } EXPORT_SYMBOL(page_pool_put_page); +void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count, + bool allow_direct) +{ + struct page *page_ring[XDP_BULK_QUEUE_SIZE]; + int i, len = 0; + + for (i = 0; i < count; i++) { + struct page *page = virt_to_head_page(data[i]); + + if (unlikely(page_ref_count(page) != 1 || + !pool_page_reusable(pool, page))) { + page_pool_release_page(pool, page); + put_page(page); + continue; + } + + if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) + page_pool_dma_sync_for_device(pool, page, -1); + + if (allow_direct && in_serving_softirq() && + page_pool_recycle_in_cache(page, pool)) + continue; + + page_ring[len++] = page; + } + + page_pool_ring_lock(pool); + for (i = 0; i < len; i++) { + if (__ptr_ring_produce(&pool->ring, page_ring[i])) + page_pool_return_page(pool, page_ring[i]); + } + page_pool_ring_unlock(pool); +} +EXPORT_SYMBOL(page_pool_put_page_bulk); + static void page_pool_empty_ring(struct page_pool *pool) { struct page *page; diff --git a/net/core/xdp.c b/net/core/xdp.c index b05467a916b4..7ebe159e3835 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -384,14 +384,13 @@ void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq, bool napi_direct) { struct xdp_mem_allocator *xa = bq->xa; - int i; - for (i = 0; i < bq->count; i++) { - napi_direct &= !xdp_return_frame_no_direct(); - page_pool_put_full_page(xa->page_pool, - virt_to_head_page(bq->q[i]), - napi_direct); - } + if (unlikely(!bq->count)) + return; + + napi_direct &= !xdp_return_frame_no_direct(); + page_pool_put_page_bulk(xa->page_pool, bq->q, bq->count, + napi_direct); bq->count = 0; } EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);